INDEX

Explanations

instances of verbs denoting communication or mental activities

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs3072-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

3,072

Data Type

torch.float32

Hook Point

blocks.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rish

-0.74

MJ

-0.69

iru

-0.67

next

-0.63

hl

-0.59

MI

-0.59

 anymore

-0.59

Zone

-0.58

Present

-0.58

-0.57

POSITIVE LOGITS

 numerous

0.97

 countless

0.95

 extensively

0.89

 since

0.86

 lately

0.86

 innumerable

0.84

 plenty

0.83

 repeatedly

0.77

 hitherto

0.75

 sufficiently

0.75

Activations Density 1.140%

instances of verbs denoting communication or mental activities

No Comments

No Known Activations